Systems and methods for a redundant array of independent disks (RAID) using a RAID circuit in cache coherent interconnect storage devices
A system is disclosed. A first storage device may supporting a cache coherent interconnect protocol, the cache coherent interconnect protocol including a block level protocol and a byte level protocol. A second storage device may also support the cache coherent interconnect protocol. A redundant array of independent disks (RAID) circuit may communicate with the first storage device and the second storage device. The RAID circuit may apply a RAID level to the first storage device and the second storage device. The RAID circuit may be configured to receive a request using the byte level protocol and to access data on the first storage device.
1. A system, comprising:
a first non-volatile storage device supporting a cache coherent interconnect protocol, the cache coherent interconnect protocol including a block level protocol and a byte level protocol;
a second non-volatile storage device supporting the cache coherent interconnect protocol; and
a redundant array of independent disks (RAID) circuit communicating with the first non-volatile storage device and the second non-volatile storage device, the RAID circuit applying a RAID level to stripe a first data across the first non-volatile storage device and the second non-volatile storage device, the RAID circuit configured to receive a request using the byte level protocol and to access a second data on the first non-volatile storage device.
2. The system according to claim 1 , wherein the cache coherent interconnect protocol includes a Compute Express Link (CXL) protocol.
3. The system according to claim 1 , further comprising a cache coherent interconnect switch, wherein the cache coherent interconnect switch is connected to the first non-volatile storage device, the second non-volatile storage device, and the RAID circuit.
4. The system according to claim 1 , further comprising a fabric manager to configure the RAID circuit.
5. The system according to claim 4 , wherein the fabric manager is configured to identify the first non-volatile storage device and the second non-volatile storage device and configure the RAID circuit to use a RAID level.
6. The system according to claim 4 , wherein the fabric manager is configured to determine a first address range of the first non-volatile storage device and a second address range of the second non-volatile storage device and to map the first address range and the second address range to a RAID address range.
7. The system according to claim 6 , wherein the fabric manager is further configured to determine the RAID address range as accessible to a processor.
8. The system according to claim 1 , wherein the RAID circuit includes a buffer.
9. The system according to claim 8 , further comprising a backup power source configured to provide backup power to the buffer.
10. The system according to claim 1 , wherein the RAID circuit is configured to return a response based at least in part on the request.
11. The system according to claim 10 , wherein:
the request includes a load request using the byte level protocol to read the second data from the first non-volatile storage device; and
the response includes the second data.
12. The system according to claim 10 , wherein:
the request includes a store request using the byte level protocol to write the second data to the first non-volatile storage device; and
the response includes a completion response.
13. The system according to claim 8 , wherein the buffer stores a first stripe of the first data across the first non-volatile storage device and the second non-volatile storage device.